Shukang Yin

xjtupanda's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a dataset about 2 months ago

xjtupanda/T2Vid-Synthetic

Preview • Updated Dec 2, 2024 • 45

updated 4 models about 2 months ago

xjtupanda/Idefics3-30K-mix-finetune

Video-Text-to-Text • Updated Dec 2, 2024 • 56

xjtupanda/Idefics3-200K-video-finetune

Video-Text-to-Text • Updated Dec 2, 2024 • 50

xjtupanda/MiniCPM-V-30K-mix-finetune

Video-Text-to-Text • Updated Dec 2, 2024 • 16

xjtupanda/MiniCPM-V-200K-video-finetune

Video-Text-to-Text • Updated Dec 2, 2024 • 12

updated a collection 2 months ago

T2Vid

Collection

T2Vid is a data augmentation method that enriches the instruction diversity of video data. In this collection, you will find related data and weights. • 5 items • Updated Nov 28, 2024

upvoted a paper over 1 year ago

Woodpecker: Hallucination Correction for Multimodal Large Language Models

Paper • 2310.16045 • Published Oct 24, 2023 • 16

authored a paper over 1 year ago

Woodpecker: Hallucination Correction for Multimodal Large Language Models

Paper • 2310.16045 • Published Oct 24, 2023 • 16